© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 236542
    Prev
    Next
    INDEX
    Explanations

    applicable options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayscale
    0.47
    0.45
    icollis
    0.42
    in
    0.42
    avio
    0.42
    -
    0.42
    媲
    0.42
    ства
    0.41
    I
    0.41
     Monmouth
    0.40
    POSITIVE LOGITS
    يال
    0.53
     sortir
    0.52
    ້ງ
    0.52
     fertiliser
    0.52
    Favourites
    0.52
     leichte
    0.51
     Счетчик
    0.51
     Spielen
    0.50
    jela
    0.50
     निकाल
    0.50
    Activations Density 0.004%

    No Known Activations